Applications of Machine Learning in Education

2021 ◽  
pp. 72-113
Author(s):  
Fatima Ali Amer Jid Almahri ◽  
David Bell ◽  
Mahir Arzoky
Keyword(s):  
Machine Learning ◽  
Student Engagement ◽  
Interaction Analysis ◽  
Design Science ◽  
Science Research ◽  
Data Driven ◽  
Persona Development ◽  
Applications Of Machine Learning ◽  
Future Work ◽  
Is Design

This research aims to explore how to enhance student engagement in higher education institutions using novel chatbots. This study's principal research methodology is design science research, which is executed in three iterations: personas elicitation, a survey and development of student engagement factor models (SEFMs), and chatbot interaction analysis. This chapter focuses on the first iteration, personas elicitation, which proposes a data-driven persona development method (DDPDM) that utilises machine learning, precisely a k-means clustering technique. Data analysis is conducted using two datasets. Eight personas are produced from the two data analyses. The pragmatic findings from this study make two contributions to the current literature. Firstly, the proposed DDPDM uses machine learning, specifically k-means clustering, to build data-driven personas. Secondly, the persona template is designed for university students, which supports the construction of data-driven personas. Future work will cover the second and third iterations.

scholarly journals Personas Design for Conversational Systems in Education

Informatics ◽  
2019 ◽  
Vol 6 (4) ◽  
pp. 46 ◽  
Author(s):  
Fatima Ali Amer Jid Almahri ◽  
David Bell ◽  
Mahir Arzoky
Keyword(s):  
Machine Learning ◽  
Student Engagement ◽  
Interaction Analysis ◽  
Design Science ◽  
Science Research ◽  
Data Driven ◽  
Gap Statistic ◽  
Optimal Value ◽  
Persona Development ◽  
Future Work

This research aims to explore how to enhance student engagement in higher education institutions (HEIs) while using a novel conversational system (chatbots). The principal research methodology for this study is design science research (DSR), which is executed in three iterations: personas elicitation, a survey and development of student engagement factor models (SEFMs), and chatbot interaction analysis. This paper focuses on the first iteration, personas elicitation, which proposes a data-driven persona development method (DDPDM) that utilises machine learning, specifically the K-means clustering technique. Data analysis is conducted using two datasets. Three methods are used to find the K-values: the elbow, gap statistic, and silhouette methods. Subsequently, the silhouette coefficient is used to find the optimal value of K. Eight personas are produced from the two data analyses. The pragmatic findings from this study make two contributions to the current literature. Firstly, the proposed DDPDM uses machine learning, specifically K-means clustering, to build data-driven personas. Secondly, the persona template is designed for university students, which supports the construction of data-driven personas. Future work will cover the second and third iterations. It will cover building SEFMs, building tailored interaction models for these personas and then evaluating them using chatbot technology.

scholarly journals Doclass: open-source software to support document labeling and classification

2020 ◽  
Author(s):  
Marcelo Inuzuka ◽  
Hugo Do Nascimento ◽  
Fernando Almeida ◽  
Bruno Barros ◽  
Walid Jradi
Keyword(s):  
Active Learning ◽  
Open Source ◽  
Open Source Software ◽  
Design Science ◽  
Text Processing ◽  
Science Research ◽  
Development Stage ◽  
Large Sets ◽  
Rest Api ◽  
Future Work

This article introduces Doclass, a free and open-source software for the Web that aims to assist in labeling and classifying large sets of documents. The research involved a design science research methodology, guided by the real demands of a legal text processing company. The architecture, several design decisions and the current development stage of the software are presented. Preliminary user experiments for evaluating interactive document labeling are described. As a result, the first version of a system with an architecture composed of a mobile frontend that communicates with a backend through a REST API was published, with satisfactory performance evaluation by the applicant. Other results involve the use of active learning techniques to reduce human effort when performing the classification of documents, as well as the Uncertainty strategy to choose the document to be labeled. The effectiveness of the stop criterion for the active learning technique based on confidence level was tested and proved unsatisfactory, remaining as a future work.

MMT

2022 ◽  
pp. 1077-1089
Author(s):  
Pekka Mäkiaho ◽  
Katriina Vartiainen ◽  
Timo Poranen
Keyword(s):  
Design Science ◽  
Science Research ◽  
Project Managers ◽  
Project Work ◽  
Software Project ◽  
Upper Management ◽  
Monitoring Software ◽  
Further Development ◽  
Is Design

This paper presents the Metrics Monitoring Tool (MMT) that was developed in university graduate and undergraduate courses on software project work in 2014-2016. The tool aims to support project members, project managers and upper management in reporting and monitoring software and project metrics for their easier and more effective utilization. The paper covers the development process of the tool, evaluation assessment, its current composition and features. The paradigm applied in this study is Design Science Research and the methods for evaluation include prototype, expert evaluation, case study and technical experiment. Data was collected from the tool users by two questionnaires. As a result, MMT was evaluated to ease the metrics handling, while several aspects related to the richness of functionalities and usability still require further development.

scholarly journals ICT IN A SOCIAL ORGANIZATION IN PANDEMIC TIMES

2021 ◽  
Author(s):  
Sara Lidon ◽  
◽  
Leonilde Reis ◽  
Clara Silveira ◽  
◽  
...  
Keyword(s):  
Social Organization ◽  
Information And Communication Technologies ◽  
Design Science ◽  
Science Research ◽  
Communication Technologies ◽  
Design Science Research ◽  
Perishable Goods ◽  
Provision Of Services ◽  
Information And Communication ◽  
Is Design

Social organizations are faced with financial problems, but also in the areas of Information Systems and Information and Communication Technologies given their support for activities in providing services to citizens. The article presents the problem in the field of the design of a multidisciplinary prototype and information aggregator to support the management of the provision of services of a Social Organization. The research methodology adopted is Design Science Research, given the specificity of the problem. Requirements models, data models, system architecture, and finally the prototype are presented. The proposed prototype aims to contribute to the reduction of regional inequalities, enhancing sustainability in the environmental, social, and human fields, as well as the inclusion of information that optimizes the reuse of non-perishable goods.

Metamodeling the e-waste domain to support decision-making

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Andrea Herrera ◽  
Paola Lara ◽  
Mario Sánchez ◽  
Jorge Villalobos
Keyword(s):  
Decision Making ◽  
Structural Model ◽  
Design Science ◽  
Conceptual Modeling ◽  
Science Research ◽  
Behavioral Model ◽  
Content Type ◽  
Domain Experts ◽  
Simulation Techniques ◽  
Is Design

PurposeThis paper proposes a conceptualization of the e-waste domain, formalized through a metamodel, to express complex e-waste realities in a simple manner. This also enables the transition from a structural model to a behavioral model to implement analysis techniques.Design/methodology/approachThe methodology used is design science research (DSR), a problem-solving paradigm which seeks to construct a working artifact and prove its relevance. The artifact, a metamodel for the e-waste domain, was constructed through an iterative manner and later analyzed to conclude its theoretical relevance and contributions in this domain. As part of the approach, the authors used supplementary techniques such as systematic literature review (SLR), conceptual modeling (CM) and system dynamics (SD).FindingsThe application in the e-waste domain of CM techniques such as metamodeling, model-to-model transformation and simulation is valuable for supporting decision-making, especially when combined with SD. The approach presented in this paper, the conceptual tools and different simulation techniques could also be applied in other complex domains to obtain similar results.Practical implicationsThe modeling method to apply simulation techniques is targeted toward the e-waste domain experts to understand, design, implement, measure and improve strategies and public policies.Originality/valueThe use of CM techniques to model and analyze structural and behavioral e-waste scenarios.

Critical Realism

2010 ◽  
pp. 57-76 ◽  
Author(s):  
Sven A. Carlsson
Keyword(s):  
Critical Realism ◽  
Design Science ◽  
Evaluation Research ◽  
Structuration Theory ◽  
Science Research ◽  
Is Research ◽  
Is Theory ◽  
Is Evaluation ◽  
Is Design ◽  
Structural Theories

Different strands of non-positivistic research approaches and theories, for example, constructivism, grounded theory, and structuration theory, have gained popularity in the information systems (IS) field. Although, they are managing to overcome some problems with positivism and structural theories they are not completely without problems. This chapter puts critical realism forward as an alternative philosophical underpinning for IS research. Critical realism starts from an ontology that identifies structures and mechanisms, through which events and discourses are generated, as being fundamental to the constitution of our natural and social reality. The chapter presents critical realism and how it can be used in IS research. Examples of how critical realism have been used and can be used in research aiming at generating new IS theory, IS evaluation research, and IS design science research are provided.

scholarly journals Self-Service Data Science in Healthcare with Automated Machine Learning

2020 ◽  
Vol 10 (9) ◽  
pp. 2992
Author(s):  
Richard Ooms ◽  
Marco Spruit
Keyword(s):  
Machine Learning ◽  
User Interfaces ◽  
Web Application ◽  
Data Science ◽  
Design Science ◽  
Science Research ◽  
Research Approach ◽  
Automated Machine Learning ◽  
Self Service ◽  
Service Data

(1) Background: This work investigates whether and how researcher-physicians can be supported in their knowledge discovery process by employing Automated Machine Learning (AutoML). (2) Methods: We take a design science research approach and select the Tree-based Pipeline Optimization Tool (TPOT) as the AutoML method based on a benchmark test and requirements from researcher-physicians. We then integrate TPOT into two artefacts: a web application and a notebook. We evaluate these artefacts with researcher-physicians to examine which approach suits researcher-physicians best. Both artefacts have a similar workflow, but different user interfaces because of a conflict in requirements. (3) Results: Artefact A, a web application, was perceived as better for uploading a dataset and comparing results. Artefact B, a Jupyter notebook, was perceived as better regarding the workflow and being in control of model construction. (4) Conclusions: Thus, a hybrid artefact would be best for researcher-physicians. However, both artefacts missed model explainability and an explanation of variable importance for their created models. Hence, deployment of AutoML technologies in healthcare remains currently limited to the exploratory data analysis phase.

Sign in / Sign up

Export Citation Format

Share Document